爬取壁纸网站（练手请勿滥用） PY源码

洪九

1. import requests
   
2. import re
   
3. url = 'https://www.bizhi88.com/3840x2160/'
   
4. headers = {
   
5.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
   
6.     }
   
7. response = requests.get(url=url, headers=headers)
   
8. response.encoding = 'utf8'
   
9. html_info = re.findall('<a href="(.*?)" title="(.*?)" target="_blank" class="img" style="(.*?)"', response.text)
   
10. num = 0
    
11. for link, title, style in html_info:
    
12.     num = num + 1
    
13.     if num == 1:
    
14.         continue
    
15.     link_url = 'https://www.bizhi88.com' + link
    
16.     response2 = requests.get(url=link_url, headers=headers)
    
17.     response2.encoding = "utf8"
    
18.     img_url = re.findall('<img src="(.*?)" alt="(.*?)"', response2.text)[0]
    
19.     print(img_url[0], img_url[1])
    
20.    

复制代码